© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39144
    Prev
    Next
    INDEX
    Explanations

    Wid

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     senses
    -0.31
     Ùħض
    -0.26
    ä½£éĩij
    -0.26
    çĿģ
    -0.25
    stakes
    -0.24
     initials
    -0.24
     MES
    -0.24
     Require
    -0.24
    éľĩèį¡
    -0.24
    -opacity
    -0.23
    POSITIVE LOGITS
    jo
    0.30
    in
    0.29
    ighb
    0.29
    atern
    0.28
    aser
    0.28
    inter
    0.28
    JO
    0.27
    lers
    0.27
    ater
    0.27
    atum
    0.27
    Activations Density 17.613%

    No Known Activations